Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only openWorldHint provided, the description carries the behavioral burden and does so richly: it discloses that title/description writes land on a TikTok-ONLY override and never rewrite the shared product record, that `dry_run` prevents writes, that `diagnosable` does not mean live (citing deactivated/deleted listings), and that tier is a US-market signal. This is well beyond what the annotation covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Long but front-loaded, leading with the purpose before the apply semantics and the diagnosable/listing_health warning. Dense prose earns most of its length, though a trailing artifact fragment and some stacking of caveats add minor noise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain returns — and it does, itemizing tier, machine-readable issues (code, how_to_solve, unlocked tier), recommendations, requirements, building_blocks, candidates, and listing_health. Nothing an agent needs to interpret results or act safely is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 67%, and the description adds real meaning to the undocumented-in-schema semantics of `apply` (safe default, hidden metadata vs merchant-visible copy) and `dry_run`. It leaves `workspace` and `store_uuid` unexplained, so it falls just short of fully compensating for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (diagnose TikTok Shop listing quality) plus the optional mutation (apply TikTok's recommendations), and implicitly distinguishes itself from siblings like auto_optimize_listings and update_product by describing the diagnosis-plus-graded-tier workflow. An agent can tell what this does without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use guidance: read-only unless `apply` is passed, `apply:['search_terms']` is the named safe default, `dry_run` previews, `issues[].fixable_by` gates action, and the tool must be re-run LATER due to async re-grading. It also routes the agent to update_product for manual title writes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.